DonorsChoose¶
DonorsChoose.org receives hundreds of thousands of project proposals each year for classroom projects in need of funding. Right now, a large number of volunteers is needed to manually screen each submission before it's approved to be posted on the DonorsChoose.org website.
Next year, DonorsChoose.org expects to receive close to 500,000 project proposals. As a result, there are three main problems they need to solve:
- How to scale current manual processes and resources to screen 500,000 projects so that they can be posted as quickly and as efficiently as possible
- How to increase the consistency of project vetting across different volunteers to improve the experience for teachers
- How to focus volunteer time on the applications that need the most assistance
The goal of the competition is to predict whether or not a DonorsChoose.org project proposal submitted by a teacher will be approved, using the text of project descriptions as well as additional metadata about the project, teacher, and school. DonorsChoose.org can then use this information to identify projects most likely to need further review before approval.
About the DonorsChoose Data Set¶
The train.csv data set provided by DonorsChoose contains the following features:
| Feature | Description |
|---|---|
project_id |
A unique identifier for the proposed project. Example: p036502 |
project_title |
Title of the project. Examples:
|
project_grade_category |
Grade level of students for which the project is targeted. One of the following enumerated values:
|
project_subject_categories |
One or more (comma-separated) subject categories for the project from the following enumerated list of values:
Examples:
|
school_state |
State where school is located (Two-letter U.S. postal code). Example: WY |
project_subject_subcategories |
One or more (comma-separated) subject subcategories for the project. Examples:
|
project_resource_summary |
An explanation of the resources needed for the project. Example:
|
project_essay_1 |
First application essay* |
project_essay_2 |
Second application essay* |
project_essay_3 |
Third application essay* |
project_essay_4 |
Fourth application essay* |
project_submitted_datetime |
Datetime when project application was submitted. Example: 2016-04-28 12:43:56.245 |
teacher_id |
A unique identifier for the teacher of the proposed project. Example: bdf8baa8fedef6bfeec7ae4ff1c15c56 |
teacher_prefix |
Teacher's title. One of the following enumerated values:
|
teacher_number_of_previously_posted_projects |
Number of project applications previously submitted by the same teacher. Example: 2 |
* See the section Notes on the Essay Data for more details about these features.
Additionally, the resources.csv data set provides more data about the resources required for each project. Each line in this file represents a resource required by a project:
| Feature | Description |
|---|---|
id |
A project_id value from the train.csv file. Example: p036502 |
description |
Desciption of the resource. Example: Tenor Saxophone Reeds, Box of 25 |
quantity |
Quantity of the resource required. Example: 3 |
price |
Price of the resource required. Example: 9.95 |
Note: Many projects require multiple resources. The id value corresponds to a project_id in train.csv, so you use it as a key to retrieve all resources needed for a project:
The data set contains the following label (the value you will attempt to predict):
| Label | Description |
|---|---|
project_is_approved |
A binary flag indicating whether DonorsChoose approved the project. A value of 0 indicates the project was not approved, and a value of 1 indicates the project was approved. |
Notes on the Essay Data¶
-
Prior to May 17, 2016, the prompts for the essays were as follows:
- __project_essay_1:__ "Introduce us to your classroom"
- __project_essay_2:__ "Tell us more about your students"
- __project_essay_3:__ "Describe how your students will use the materials you're requesting"
- __project_essay_4:__ "Close by sharing why your project will make a difference"
-
Starting on May 17, 2016, the number of essays was reduced from 4 to 2, and the prompts for the first 2 essays were changed to the following:
- __project_essay_1:__ "Describe your students: What makes your students special? Specific details about their background, your neighborhood, and your school are all helpful."
- __project_essay_2:__ "About your project: How will these materials make a difference in your students' learning and improve their school lives?"
For all projects with project_submitted_datetime of 2016-05-17 and later, the values of project_essay_3 and project_essay_4 will be NaN.
In [116]:
%matplotlib inline
import warnings
warnings.filterwarnings("ignore")
import sqlite3
import pandas as pd
import numpy as np
import nltk
import string
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics import confusion_matrix
from sklearn import metrics
from sklearn.metrics import roc_curve, auc
from nltk.stem.porter import PorterStemmer
import re
# Tutorial about Python regular expressions: https://pymotw.com/2/re/
import string
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
from nltk.stem.wordnet import WordNetLemmatizer
from gensim.models import Word2Vec
from gensim.models import KeyedVectors
import pickle
from tqdm import tqdm
import os
from plotly import plotly
import plotly.offline as offline
import plotly.graph_objs as go
offline.init_notebook_mode()
from collections import Counter
1.1 Reading Data¶
In [117]:
project_data = pd.read_csv('train_data.csv')
resource_data = pd.read_csv('resources.csv')
In [118]:
print("Number of data points in train data", project_data.shape)
print('-'*50)
print("The attributes of data :", project_data.columns.values)
In [119]:
print("Number of data points in train data", resource_data.shape)
print(resource_data.columns.values)
resource_data.head(2)
Out[119]:
1.2 Data Analysis¶
In [120]:
# PROVIDE CITATIONS TO YOUR CODE IF YOU TAKE IT FROM ANOTHER WEBSITE.
# https://matplotlib.org/gallery/pie_and_polar_charts/pie_and_donut_labels.html#sphx-glr-gallery-pie-and-polar-charts-pie-and-donut-labels-py
y_value_counts = project_data['project_is_approved'].value_counts()
print("Number of projects thar are approved for funding ", y_value_counts[1], ", (", (y_value_counts[1]/(y_value_counts[1]+y_value_counts[0]))*100,"%)")
print("Number of projects thar are not approved for funding ", y_value_counts[0], ", (", (y_value_counts[0]/(y_value_counts[1]+y_value_counts[0]))*100,"%)")
fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(aspect="equal"))
recipe = ["Accepted", "Not Accepted"]
data = [y_value_counts[1], y_value_counts[0]]
wedges, texts = ax.pie(data, wedgeprops=dict(width=0.5), startangle=-40)
bbox_props = dict(boxstyle="square,pad=0.3", fc="w", ec="k", lw=0.72)
kw = dict(xycoords='data', textcoords='data', arrowprops=dict(arrowstyle="-"),
bbox=bbox_props, zorder=0, va="center")
for i, p in enumerate(wedges):
ang = (p.theta2 - p.theta1)/2. + p.theta1
y = np.sin(np.deg2rad(ang))
x = np.cos(np.deg2rad(ang))
horizontalalignment = {-1: "right", 1: "left"}[int(np.sign(x))]
connectionstyle = "angle,angleA=0,angleB={}".format(ang)
kw["arrowprops"].update({"connectionstyle": connectionstyle})
ax.annotate(recipe[i], xy=(x, y), xytext=(1.35*np.sign(x), 1.4*y),
horizontalalignment=horizontalalignment, **kw)
ax.set_title("Nmber of projects that are Accepted and not accepted")
plt.show()
1.2.1 Univariate Analysis: School State¶
In [121]:
# Pandas dataframe groupby count, mean: https://stackoverflow.com/a/19385591/4084039
temp = pd.DataFrame(project_data.groupby("school_state")["project_is_approved"].apply(np.mean)).reset_index()
# if you have data which contain only 0 and 1, then the mean = percentage (think about it)
temp.columns = ['state_code', 'num_proposals']
'''# How to plot US state heatmap: https://datascience.stackexchange.com/a/9620
scl = [[0.0, 'rgb(242,240,247)'],[0.2, 'rgb(218,218,235)'],[0.4, 'rgb(188,189,220)'],\
[0.6, 'rgb(158,154,200)'],[0.8, 'rgb(117,107,177)'],[1.0, 'rgb(84,39,143)']]
data = [ dict(
type='choropleth',
colorscale = scl,
autocolorscale = False,
locations = temp['state_code'],
z = temp['num_proposals'].astype(float),
locationmode = 'USA-states',
text = temp['state_code'],
marker = dict(line = dict (color = 'rgb(255,255,255)',width = 2)),
colorbar = dict(title = "% of pro")
) ]
layout = dict(
title = 'Project Proposals % of Acceptance Rate by US States',
geo = dict(
scope='usa',
projection=dict( type='albers usa' ),
showlakes = True,
lakecolor = 'rgb(255, 255, 255)',
),
)
fig = go.Figure(data=data, layout=layout)
offline.iplot(fig, filename='us-map-heat-map')
'''
Out[121]:
In [122]:
# https://www.csi.cuny.edu/sites/default/files/pdf/administration/ops/2letterstabbrev.pdf
temp.sort_values(by=['num_proposals'], inplace=True)
print("States with lowest % approvals")
print(temp.head(5))
print('='*50)
print("States with highest % approvals")
print(temp.tail(5))
SUMMARY :¶
- Delaware (DE) state from the United States has the highest percent of projects accepted almost 90%, followed by North Dakota (ND) and Washington (WA) nearly 89% and 88% respectively each
- Vermont (VT) has the lowest Approval rate with exactly 80% followed by District of Columbia (DC) and Texas (TX) with nearly 80% and 81% respectively.
In [123]:
#stacked bar plots matplotlib: https://matplotlib.org/gallery/lines_bars_and_markers/bar_stacked.html
def stack_plot(data, xtick, col2='project_is_approved', col3='total'):
ind = np.arange(data.shape[0])
plt.figure(figsize=(20,5))
p1 = plt.bar(ind, data[col3].values)
p2 = plt.bar(ind, data[col2].values)
plt.ylabel('Projects')
plt.title('Number of projects aproved vs rejected')
plt.xticks(ind, list(data[xtick].values))
plt.legend((p1[0], p2[0]), ('total', 'accepted'))
plt.show()
In [124]:
def univariate_barplots(data, col1, col2='project_is_approved', top=False):
# Count number of zeros in dataframe python: https://stackoverflow.com/a/51540521/4084039
temp = pd.DataFrame(project_data.groupby(col1)[col2].agg(lambda x: x.eq(1).sum())).reset_index()
# Pandas dataframe grouby count: https://stackoverflow.com/a/19385591/4084039
temp['total'] = pd.DataFrame(project_data.groupby(col1)[col2].agg({'total':'count'})).reset_index()['total']
temp['Avg'] = pd.DataFrame(project_data.groupby(col1)[col2].agg({'Avg':'mean'})).reset_index()['Avg']
temp.sort_values(by=['total'],inplace=True, ascending=False)
if top:
temp = temp[0:top]
stack_plot(temp, xtick=col1, col2=col2, col3='total')
print(temp.head(5))
print("="*50)
print(temp.tail(5))
In [125]:
univariate_barplots(project_data, 'school_state', 'project_is_approved', False)
SUMMARY: Every state has greater than 80% success rate in approval
- California(CA) has the highest number of project proposals when compared to the other states, Surprisingly, 85% of the projects gets approved on an average
- Vermont(VT) has the lowest number of project proposals initiated
1.2.2 Univariate Analysis: teacher_prefix¶
In [126]:
univariate_barplots(project_data, 'teacher_prefix', 'project_is_approved' , top=False)
SUMMARY :
- Female Teachers have the maximum number of projects proposed and accepted compared to the male teachers.
- Teachers with prefixes Mrs. , which means Married Women as teachers have a higher number of projects Proposed as well as Accepted when compared to the younger Unmarried Women Teachers.
1.2.3 Univariate Analysis: project_grade_category¶
In [127]:
univariate_barplots(project_data, 'project_grade_category', 'project_is_approved', top=False)
Summary :-
- There are alot of projects proposed for the students between Pre Kindergarden and 2nd Grade while for the rest it keeps decreasing.
- The average Acceptance rate of the project is 84% irrespective of the Grade.
- We also notice that Students between the 9th Grade and 12th Grade have the lowest number of projects proposed as well as accepted.
1.2.4 Univariate Analysis: project_subject_categories¶
In [128]:
catogories = list(project_data['project_subject_categories'].values)
# remove special characters from list of strings python: https://stackoverflow.com/a/47301924/4084039
# https://www.geeksforgeeks.org/removing-stop-words-nltk-python/
# https://stackoverflow.com/questions/23669024/how-to-strip-a-specific-word-from-a-string
# https://stackoverflow.com/questions/8270092/remove-all-whitespace-in-a-string-in-python
cat_list = []
for i in catogories:
temp = ""
# consider we have text like this "Math & Science, Warmth, Care & Hunger"
for j in i.split(','): # it will split it in three parts ["Math & Science", "Warmth", "Care & Hunger"]
if 'The' in j.split(): # this will split each of the catogory based on space "Math & Science"=> "Math","&", "Science"
j=j.replace('The','') # if we have the words "The" we are going to replace it with ''(i.e removing 'The')
j = j.replace(' ','') # we are placeing all the ' '(space) with ''(empty) ex:"Math & Science"=>"Math&Science"
temp+=j.strip()+" " #" abc ".strip() will return "abc", remove the trailing spaces
temp = temp.replace('&','_') # we are replacing the & value into
cat_list.append(temp.strip())
In [129]:
project_data['clean_categories'] = cat_list
project_data.drop(['project_subject_categories'], axis=1, inplace=True)
project_data.head(2)
Out[129]:
In [130]:
univariate_barplots(project_data, 'clean_categories', 'project_is_approved', top=20)
In [131]:
# count of all the words in corpus python: https://stackoverflow.com/a/22898595/4084039
from collections import Counter
my_counter = Counter()
for word in project_data['clean_categories'].values:
my_counter.update(word.split())
In [132]:
# dict sort by value python: https://stackoverflow.com/a/613218/4084039
cat_dict = dict(my_counter)
sorted_cat_dict = dict(sorted(cat_dict.items(), key=lambda kv: kv[1]))
ind = np.arange(len(sorted_cat_dict))
plt.figure(figsize=(20,5))
p1 = plt.bar(ind, list(sorted_cat_dict.values()))
plt.ylabel('Projects')
plt.title('% of projects aproved category wise')
plt.xticks(ind, list(sorted_cat_dict.keys()))
plt.show()
In [133]:
for i, j in sorted_cat_dict.items():
print("{:20} :{:10}".format(i,j))
SUMMARY :
- The highest number of projects are registered under Literacy and Language with 52,239 projects, followed by Maths and Science having 41,421 projects.
- There are only 1388 projects under the category of Warmth , Care or Hunger.
1.2.5 Univariate Analysis: project_subject_subcategories¶
In [134]:
sub_catogories = list(project_data['project_subject_subcategories'].values)
# remove special characters from list of strings python: https://stackoverflow.com/a/47301924/4084039
# https://www.geeksforgeeks.org/removing-stop-words-nltk-python/
# https://stackoverflow.com/questions/23669024/how-to-strip-a-specific-word-from-a-string
# https://stackoverflow.com/questions/8270092/remove-all-whitespace-in-a-string-in-python
sub_cat_list = []
for i in sub_catogories:
temp = ""
# consider we have text like this "Math & Science, Warmth, Care & Hunger"
for j in i.split(','): # it will split it in three parts ["Math & Science", "Warmth", "Care & Hunger"]
if 'The' in j.split(): # this will split each of the catogory based on space "Math & Science"=> "Math","&", "Science"
j=j.replace('The','') # if we have the words "The" we are going to replace it with ''(i.e removing 'The')
j = j.replace(' ','') # we are placeing all the ' '(space) with ''(empty) ex:"Math & Science"=>"Math&Science"
temp +=j.strip()+" "#" abc ".strip() will return "abc", remove the trailing spaces
temp = temp.replace('&','_')
sub_cat_list.append(temp.strip())
In [135]:
project_data['clean_subcategories'] = sub_cat_list
project_data.drop(['project_subject_subcategories'], axis=1, inplace=True)
project_data.head(2)
Out[135]:
In [136]:
univariate_barplots(project_data, 'clean_subcategories', 'project_is_approved', top=50)
SUMMARY :
- The sub-Category Literacy has the highest number of projects approved with 8371 projects. Also the acceptance rate is 88%.
In [137]:
# count of all the words in corpus python: https://stackoverflow.com/a/22898595/4084039
from collections import Counter
my_counter = Counter()
for word in project_data['clean_subcategories'].values:
my_counter.update(word.split())
In [138]:
# dict sort by value python: https://stackoverflow.com/a/613218/4084039
sub_cat_dict = dict(my_counter)
sorted_sub_cat_dict = dict(sorted(sub_cat_dict.items(), key=lambda kv: kv[1]))
ind = np.arange(len(sorted_sub_cat_dict))
plt.figure(figsize=(20,5))
p1 = plt.bar(ind, list(sorted_sub_cat_dict.values()))
plt.ylabel('Projects')
plt.title('% of projects aproved state wise')
plt.xticks(ind, list(sorted_sub_cat_dict.keys()))
plt.show()
In [139]:
for i, j in sorted_sub_cat_dict.items():
print("{:20} :{:10}".format(i,j))
1.2.6 Univariate Analysis: Text features (Title)¶
In [140]:
#How to calculate number of words in a string in DataFrame: https://stackoverflow.com/a/37483537/4084039
word_count = project_data['project_title'].str.split().apply(len).value_counts()
word_dict = dict(word_count)
word_dict = dict(sorted(word_dict.items(), key=lambda kv: kv[1]))
ind = np.arange(len(word_dict))
plt.figure(figsize=(20,5))
p1 = plt.bar(ind, list(word_dict.values()))
plt.ylabel('Numeber of projects')
plt.xlabel('Numeber words in project title')
plt.title('Words for each title of the project')
plt.xticks(ind, list(word_dict.keys()))
plt.show()
SUMMARY :
- Most of the projects have 4 words in the title.
- Roughly most of the projects have 3, 4 or 5 words in the title.
- There are hardly any project titles containing more than 10 words.
In [141]:
approved_title_word_count = project_data[project_data['project_is_approved']==1]['project_title'].str.split().apply(len)
approved_title_word_count = approved_title_word_count.values
rejected_title_word_count = project_data[project_data['project_is_approved']==0]['project_title'].str.split().apply(len)
rejected_title_word_count = rejected_title_word_count.values
In [142]:
# https://glowingpython.blogspot.com/2012/09/boxplot-with-matplotlib.html
plt.boxplot([approved_title_word_count, rejected_title_word_count])
plt.xticks([1,2],('Approved Projects','Rejected Projects'))
plt.ylabel('Words in project title')
plt.grid()
plt.show()
In [143]:
plt.figure(figsize=(10,3))
sns.kdeplot(approved_title_word_count,label="Approved Projects", bw=0.6)
sns.kdeplot(rejected_title_word_count,label="Not Approved Projects", bw=0.6)
plt.legend()
plt.show()
SUMMARY : The number of Projects approved have a slightly more number of words in the Title when compared to the Rejected Projects. The Boxplots use the Percentiles while the above graph used Probability densities.
1.2.7 Univariate Analysis: Text features (Project Essay's)¶
In [144]:
# merge two column text dataframe:
project_data["essay"] = project_data["project_essay_1"].map(str) +\
project_data["project_essay_2"].map(str) + \
project_data["project_essay_3"].map(str) + \
project_data["project_essay_4"].map(str)
In [145]:
approved_word_count = project_data[project_data['project_is_approved']==1]['essay'].str.split().apply(len)
approved_word_count = approved_word_count.values
rejected_word_count = project_data[project_data['project_is_approved']==0]['essay'].str.split().apply(len)
rejected_word_count = rejected_word_count.values
In [146]:
# https://glowingpython.blogspot.com/2012/09/boxplot-with-matplotlib.html
plt.boxplot([approved_word_count, rejected_word_count])
plt.title('Words for each essay of the project')
plt.xticks([1,2],('Approved Projects','Rejected Projects'))
plt.ylabel('Words in project essays')
plt.grid()
plt.show()
SUMMARY :
Approved projects have a slightly more number of words in the project essays when compared to the projects that have not been approved. This difference can be noticed in the percentile difference after the 50.0
In [147]:
plt.figure(figsize=(10,3))
sns.distplot(approved_word_count, hist=False, label="Approved Projects")
sns.distplot(rejected_word_count, hist=False, label="Not Approved Projects")
plt.title('Words for each essay of the project')
plt.xlabel('Number of words in each eassay')
plt.legend()
plt.show()
SUMMARY :
The number of words in the Project Essays of Approved Projects are slightly more than the number of words in the Project Essays of the Rejected Projects. This can be noticed by looking at the Blue Line (PDF Curve of Approved Projects) which is denser for words more than 240 to almost 480 or 500.
1.2.8 Univariate Analysis: Cost per project¶
In [148]:
# we get the cost of the project using resource.csv file
resource_data.head(2)
Out[148]:
In [149]:
# https://stackoverflow.com/questions/22407798/how-to-reset-a-dataframes-indexes-for-all-groups-in-one-step
price_data = resource_data.groupby('id').agg({'price':'sum', 'quantity':'sum'}).reset_index()
price_data.head(2)
Out[149]:
In [150]:
# join two dataframes in python:
project_data = pd.merge(project_data, price_data, on='id', how='left')
In [151]:
approved_price = project_data[project_data['project_is_approved']==1]['price'].values
rejected_price = project_data[project_data['project_is_approved']==0]['price'].values
In [152]:
# https://glowingpython.blogspot.com/2012/09/boxplot-with-matplotlib.html
plt.boxplot([approved_price, rejected_price])
plt.title('Box Plots of Cost per approved and not approved Projects')
plt.xticks([1,2],('Approved Projects','Rejected Projects'))
plt.ylabel('Price')
plt.grid()
plt.show()
In [153]:
plt.figure(figsize=(10,3))
sns.distplot(approved_price, hist=False, label="Approved Projects")
sns.distplot(rejected_price, hist=False, label="Not Approved Projects")
plt.title('Cost per approved and not approved Projects')
plt.xlabel('Cost of a project')
plt.legend()
plt.show()
In [154]:
# http://zetcode.com/python/prettytable/
from prettytable import PrettyTable
#If you get a ModuleNotFoundError error , install prettytable using: pip3 install prettytable
x = PrettyTable()
x.field_names = ["Percentile", "Approved Projects", "Not Approved Projects"]
for i in range(0,101,5):
x.add_row([i,np.round(np.percentile(approved_price,i), 3), np.round(np.percentile(rejected_price,i), 3)])
print(x)
SUMMARY :
- The approved projects tend to have lower cost when compared to the projects that have not been approved. This can be noticed by looking at the percentile values. The 50th percentile Cost value for an approved project is 199 dollars while for the cost for the not approved projects is 263 dollars.
- The Maximum price for any project should be less than 10,000 dollars.
- Typically, any approved Project costs less than the that of the Projects not approved across the spectrum of Percentiles.
1.2.9 Univariate Analysis: teacher_number_of_previously_posted_projects
Please do this on your own based on the data analysis that was done in the above cells
In [155]:
univariate_barplots(project_data, 'teacher_number_of_previously_posted_projects', 'project_is_approved' , top=False)
SUMMARY :
- We observe that it is not mandatory for a teacher to have proposed any project prior. Maximum number of teachers, nearly 82% of the approved projects have been submitted by teachers with no prior project proposals. New talent and efforts are well appreciated.
- Very few teachers who have proposed more than 20 projects have got approval. But the rate of approval is Higher given the teacher has proposed atleast 19 different projects.
In [156]:
#filter the project based on counts
zero_count_project = project_data[project_data['teacher_number_of_previously_posted_projects']==0]
one_count_project = project_data[project_data['teacher_number_of_previously_posted_projects']==1]
more_than_one_count_project = project_data[project_data['teacher_number_of_previously_posted_projects'] > 1]
In [157]:
#approved percentage count based on previouly submitted project data
print("Percentage of teachers with their 1st Project", (float(zero_count_project.shape[0] / project_data.shape[0])*100))
print("Percentage of teachers with only one Project", (float(one_count_project.shape[0] / project_data.shape[0])*100))
print("Percentage of teachers with more than one Projects", (float(more_than_one_count_project.shape[0] / project_data.shape[0])*100))
In [158]:
plt.figure(figsize = (10, 3))
sns.distplot(project_data['teacher_number_of_previously_posted_projects'])
plt.title('Histogram of number of previously posted applications by the submitting teacher')
plt.xlabel('Number of previously posted applications by the submitting teacher', fontsize=12)
plt.ylabel('Count', fontsize=12)
plt.show()
In [159]:
#keywords: - sort the values into bins pandas : https://dfrieds.com/data-analysis/bin-values-python-pandas
project_data['#previously_posted_range'] = pd.cut(project_data["teacher_number_of_previously_posted_projects"],bins=[-1,1,5,10,25,50,100,500],
labels=['0-1','2-5','6-10','11-25','26-50','51-100','100+'])
previously_posted_range = pd.DataFrame(project_data.groupby('#previously_posted_range')['project_is_approved'].count())
previously_posted_range
Out[159]:
In [160]:
#sum the approved project , apporved = 1 , not approved = 0
previously_posted_range['#approved'] = project_data.groupby('#previously_posted_range')['project_is_approved'].sum()
In [161]:
project_data['#previously_posted_range'].head(10)
Out[161]:
In [162]:
previously_posted_range['#not_approved'] = previously_posted_range['project_is_approved'] - previously_posted_range['#approved']
previously_posted_range['#approved%'] = (previously_posted_range['#approved']/previously_posted_range['project_is_approved']) * 100
previously_posted_range['#approved%']
Out[162]:
In [163]:
axA = previously_posted_range[['project_is_approved','#approved','#not_approved']].plot(kind='bar', figsize=(12,6),
legend=True, fontsize=16, title='Number of Previously Posted Projects')
axB = previously_posted_range['#approved%'].plot(kind='line', secondary_y=True, fontsize=14, color='r', legend=True, alpha=1.0)
axA.set_xlabel('Number of Prior Projects Posted by Teacher', fontsize=16)
axA.set_ylabel('Number of Submitted Projects', fontsize=16)
axB.set_ylabel('Percentage Projects Approved', fontsize=16)
axB.set_ylim(70,100)
Out[163]:
1.2.10 Univariate Analysis: project_resource_summary
Please do this on your own based on the data analysis that was done in the above cells
Check if the presence of the numerical digits in the project_resource_summary effects the acceptance of the project or not. If you observe that presence of the numerical digits is helpful in the classification, please include it for further process or you can ignore it.
1.3 Text preprocessing¶
1.3.1 Essay Text¶
In [164]:
project_data.head(2)
Out[164]:
In [165]:
# printing some random essays.
print(project_data['essay'].values[0])
print("="*50)
print(project_data['essay'].values[150])
print("="*50)
print(project_data['essay'].values[1000])
print("="*50)
print(project_data['essay'].values[20000])
print("="*50)
print(project_data['essay'].values[99999])
print("="*50)
In [166]:
# https://stackoverflow.com/a/47091490/4084039
import re
def decontracted(phrase):
# specific
phrase = re.sub(r"won't", "will not", phrase)
phrase = re.sub(r"can\'t", "can not", phrase)
# general
phrase = re.sub(r"n\'t", " not", phrase)
phrase = re.sub(r"\'re", " are", phrase)
phrase = re.sub(r"\'s", " is", phrase)
phrase = re.sub(r"\'d", " would", phrase)
phrase = re.sub(r"\'ll", " will", phrase)
phrase = re.sub(r"\'t", " not", phrase)
phrase = re.sub(r"\'ve", " have", phrase)
phrase = re.sub(r"\'m", " am", phrase)
return phrase
In [167]:
sent = decontracted(project_data['essay'].values[20000])
print(sent)
print("="*50)
In [168]:
# \r \n \t remove from string python: http://texthandler.com/info/remove-line-breaks-python/
sent = sent.replace('\\r', ' ')
sent = sent.replace('\\"', ' ')
sent = sent.replace('\\n', ' ')
print(sent)
In [169]:
#remove spacial character: https://stackoverflow.com/a/5843547/4084039
sent = re.sub('[^A-Za-z0-9]+', ' ', sent)
print(sent)
In [170]:
# https://gist.github.com/sebleier/554280
# we are removing the words from the stop words list: 'no', 'nor', 'not'
stopwords= ['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've",\
"you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', \
'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their',\
'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', \
'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', \
'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', \
'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after',\
'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further',\
'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more',\
'most', 'other', 'some', 'such', 'only', 'own', 'same', 'so', 'than', 'too', 'very', \
's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', \
've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn',\
"hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn',\
"mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", \
'won', "won't", 'wouldn', "wouldn't"]
In [171]:
# Combining all the above statemennts
from tqdm import tqdm
preprocessed_essays = []
# tqdm is for printing the status bar
for sentance in tqdm(project_data['essay'].values):
sent = decontracted(sentance)
sent = sent.replace('\\r', ' ')
sent = sent.replace('\\"', ' ')
sent = sent.replace('\\n', ' ')
sent = re.sub('[^A-Za-z0-9]+', ' ', sent)
# https://gist.github.com/sebleier/554280
sent = ' '.join(e for e in sent.split() if e not in stopwords)
preprocessed_essays.append(sent.lower().strip())
In [172]:
# after preprocesing
preprocessed_essays[20000]
Out[172]:
1.3.2 Project title Text
In [173]:
# similarly you can preprocess the titles also
project_data["project_title"][0:10]
Out[173]:
In [174]:
# Combining all the above statemennts
from tqdm import tqdm
preprocessed_projectTitle = []
# tqdm is for printing the status bar
for sentance in tqdm(project_data['project_title'].values):
sent = decontracted(sentance)
sent = sent.replace('\\r', ' ')
sent = sent.replace('\\"', ' ')
sent = sent.replace('\\n', ' ')
sent = re.sub('[^A-Za-z0-9]+', ' ', sent)
# https://gist.github.com/sebleier/554280
sent = ' '.join(e for e in sent.split() if e not in stopwords)
preprocessed_projectTitle.append(sent.lower().strip())
In [175]:
preprocessed_projectTitle[0:20]
Out[175]:
1. 4 Preparing data for models¶
In [176]:
project_data.columns
Out[176]:
we are going to consider
- school_state : categorical data
- clean_categories : categorical data
- clean_subcategories : categorical data
- project_grade_category : categorical data
- teacher_prefix : categorical data
- project_title : text data
- text : text data
- project_resource_summary: text data
- quantity : numerical
- teacher_number_of_previously_posted_projects : numerical
- price : numerical1.4.1 Vectorizing Categorical data¶
In [177]:
# we use count vectorizer to convert the values into one hot encoded features
from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer(vocabulary=list(sorted_cat_dict.keys()), lowercase=False, binary=True)
vectorizer.fit(project_data['clean_categories'].values)
print(vectorizer.get_feature_names())
categories_one_hot = vectorizer.transform(project_data['clean_categories'].values)
print("Shape of matrix after one hot encodig ",categories_one_hot.shape)
In [178]:
# we use count vectorizer to convert the values into one hot encoded features
vectorizer = CountVectorizer(vocabulary=list(sorted_sub_cat_dict.keys()), lowercase=False, binary=True)
vectorizer.fit(project_data['clean_subcategories'].values)
print(vectorizer.get_feature_names())
sub_categories_one_hot = vectorizer.transform(project_data['clean_subcategories'].values)
print("Shape of matrix after one hot encodig ",sub_categories_one_hot.shape)
In [179]:
# Please do the similar feature encoding with state, teacher_prefix and project_grade_category also
In [180]:
# count of all the words in corpus python: https://stackoverflow.com/a/22898595/4084039
from collections import Counter
my_counter = Counter()
for word in project_data['school_state'].values:
my_counter.update(word.split())
# dict sort by value python: https://stackoverflow.com/a/613218/4084039
school_state_dict = dict(my_counter)
sorted_school_state_dict = dict(sorted(school_state_dict.items(), key=lambda kv: kv[1]))
In [181]:
# one hot encoding for school state
vectorizer = CountVectorizer(vocabulary=list(sorted_school_state_dict.keys()), lowercase=False, binary=True)
vectorizer.fit(project_data['school_state'].values)
print(vectorizer.get_feature_names())
school_state_one_hot = vectorizer.transform(project_data['school_state'].values)
print("Shape of matrix after one hot encodig ",school_state_one_hot.shape)
In [182]:
# one hot encoding for teacher_prefix
project_data['teacher_prefix'].unique()
#https://stackoverflow.com/questions/30267834/df-fillna0-command-wont-replace-nan-values-with-0
#https://pandas.pydata.org/pandas-docs/stable/user_guide/missing_data.html
project_data_teacher_prefix = project_data['teacher_prefix'].fillna(' ')
project_data_teacher_prefix.unique()
project_data[7820:7821]
Out[182]:
In [183]:
#one hot encoding for teacher prefix
# count of all the words in corpus python: https://stackoverflow.com/a/22898595/4084039
from collections import Counter
my_counter = Counter()
for word in project_data_teacher_prefix:
my_counter.update(word.split())
# dict sort by value python: https://stackoverflow.com/a/613218/4084039
teacher_prefix_dict = dict(my_counter)
sorted_teacher_prefix_dict = dict(sorted(teacher_prefix_dict.items(), key=lambda kv: kv[1]))
# one hot encoding for school state
vectorizer = CountVectorizer(vocabulary=list(sorted_teacher_prefix_dict.keys()), lowercase=False, binary=True)
vectorizer.fit(project_data_teacher_prefix)
print(vectorizer.get_feature_names())
teacher_prefix_one_hot = vectorizer.transform(project_data_teacher_prefix)
print("Shape of matrix after one hot encodig ",teacher_prefix_one_hot.shape)
In [184]:
#one hot encoding for project_grade_category
#project_data['project_grade_category'][:30]
from collections import Counter
my_counter = Counter()
for word in project_data['project_grade_category']:
my_counter.update(word.split())
# dict sort by value python: https://stackoverflow.com/a/613218/4084039
project_grade_category_dict = dict(my_counter)
sorted_project_grade_category_dict = dict(sorted(project_grade_category_dict.items(), key=lambda kv: kv[1]))
vectorizer = CountVectorizer(vocabulary=list(sorted_project_grade_category_dict.keys()), lowercase=False, binary=True)
vectorizer.fit(project_data['project_grade_category'])
print(vectorizer.get_feature_names())
project_grade_category_one_hot = vectorizer.transform(project_data['project_grade_category'])
print("Shape of matrix after one hot encodig ",project_grade_category_one_hot.shape)
1.4.2 Vectorizing Text data¶
1.4.2.1 Bag of words¶
In [185]:
# We are considering only the words which appeared in at least 10 documents(rows or projects).
vectorizer = CountVectorizer(min_df=10)
text_bow_vec = vectorizer.fit_transform(preprocessed_essays)
print("Shape of matrix after one hot encodig ",text_bow_vec.shape)
1.4.2.2 Bag of Words on `project_title`
In [186]:
# you can vectorize the title also
# before you vectorize the title make sure you preprocess it
vectorizer = CountVectorizer(min_df=10)
In [187]:
# Similarly you can vectorize for title also
project_title_bow_vec = vectorizer.fit_transform(preprocessed_projectTitle)
print("Shape of matrix after vectorizer ",project_title_bow_vec.shape)
1.4.2.3 TFIDF vectorizer¶
In [188]:
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(min_df=10)
text_tfidf = vectorizer.fit_transform(preprocessed_essays)
print("Shape of matrix after vectorizer ",text_tfidf.shape)
1.4.2.4 TFIDF Vectorizer on `project_title`
In [189]:
# Similarly you can vectorize for title also
vectorizer = TfidfVectorizer(min_df=10)
project_title_tfidf_vec = vectorizer.fit_transform(preprocessed_projectTitle )
print("Shape of matrix after vectorizer ",project_title_tfidf_vec.shape)
1.4.2.5 Using Pretrained Models: Avg W2V¶
In [190]:
'''
# Reading glove vectors in python: https://stackoverflow.com/a/38230349/4084039
def loadGloveModel(gloveFile):
print ("Loading Glove Model")
f = open(gloveFile,'r', encoding="utf8")
model = {}
for line in tqdm(f):
splitLine = line.split()
word = splitLine[0]
embedding = np.array([float(val) for val in splitLine[1:]])
model[word] = embedding
print ("Done.",len(model)," words loaded!")
return model
model = loadGloveModel('glove.42B.300d.txt')
# ============================
Output:
Loading Glove Model
1917495it [06:32, 4879.69it/s]
Done. 1917495 words loaded!
# ============================
words = []
for i in preproced_texts:
words.extend(i.split(' '))
for i in preproced_titles:
words.extend(i.split(' '))
print("all the words in the coupus", len(words))
words = set(words)
print("the unique words in the coupus", len(words))
inter_words = set(model.keys()).intersection(words)
print("The number of words that are present in both glove vectors and our coupus", \
len(inter_words),"(",np.round(len(inter_words)/len(words)*100,3),"%)")
words_courpus = {}
words_glove = set(model.keys())
for i in words:
if i in words_glove:
words_courpus[i] = model[i]
print("word 2 vec length", len(words_courpus))
# stronging variables into pickle files python: http://www.jessicayung.com/how-to-use-pickle-to-save-and-load-variables-in-python/
import pickle
with open('glove_vectors', 'wb') as f:
pickle.dump(words_courpus, f)
'''
Out[190]:
In [191]:
# stronging variables into pickle files python: http://www.jessicayung.com/how-to-use-pickle-to-save-and-load-variables-in-python/
# make sure you have the glove_vectors file
with open('glove_vectors', 'rb') as f:
model = pickle.load(f)
glove_words = set(model.keys())
In [192]:
# average Word2Vec
# compute average word2vec for each review.
avg_w2v_vectors = []; # the avg-w2v for each sentence/review is stored in this list
for sentence in tqdm(preprocessed_essays): # for each review/sentence
vector = np.zeros(300) # as word vectors are of zero length
cnt_words =0; # num of words with a valid vector in the sentence/review
for word in sentence.split(): # for each word in a review/sentence
if word in glove_words:
vector += model[word]
cnt_words += 1
if cnt_words != 0:
vector /= cnt_words
avg_w2v_vectors.append(vector)
print(len(avg_w2v_vectors))
print(len(avg_w2v_vectors[0]))
1.4.2.6 Using Pretrained Models: AVG W2V on `project_title`
In [193]:
# Similarly you can vectorize for title also
avg_w2v_vectors_project_title = []; # the avg-w2v for each sentence/review is stored in this list
for sentence in tqdm(preprocessed_projectTitle): # for each review/sentence
vector = np.zeros(300) # as word vectors are of zero length
cnt_words =0; # num of words with a valid vector in the sentence/review
for word in sentence.split(): # for each word in a review/sentence
if word in glove_words:
vector += model[word]
cnt_words += 1
if cnt_words != 0:
vector /= cnt_words
avg_w2v_vectors_project_title.append(vector)
print(len(avg_w2v_vectors_project_title))
print(len(avg_w2v_vectors_project_title[0]))
1.4.2.7 Using Pretrained Models: TFIDF weighted W2V¶
In [194]:
# S = ["abc def pqr", "def def def abc", "pqr pqr def"]
tfidf_model = TfidfVectorizer()
tfidf_model.fit(preprocessed_essays)
# we are converting a dictionary with word as a key, and the idf as a value
dictionary = dict(zip(tfidf_model.get_feature_names(), list(tfidf_model.idf_)))
tfidf_words = set(tfidf_model.get_feature_names())
In [195]:
# average Word2Vec
# compute average word2vec for each review.
tfidf_w2v_vectors = []; # the avg-w2v for each sentence/review is stored in this list
for sentence in tqdm(preprocessed_essays): # for each review/sentence
vector = np.zeros(300) # as word vectors are of zero length
tf_idf_weight =0; # num of words with a valid vector in the sentence/review
for word in sentence.split(): # for each word in a review/sentence
if (word in glove_words) and (word in tfidf_words):
vec = model[word] # getting the vector for each word
# here we are multiplying idf value(dictionary[word]) and the tf value((sentence.count(word)/len(sentence.split())))
tf_idf = dictionary[word]*(sentence.count(word)/len(sentence.split())) # getting the tfidf value for each word
vector += (vec * tf_idf) # calculating tfidf weighted w2v
tf_idf_weight += tf_idf
if tf_idf_weight != 0:
vector /= tf_idf_weight
tfidf_w2v_vectors.append(vector)
print(len(tfidf_w2v_vectors))
print(len(tfidf_w2v_vectors[0]))
1.4.2.9 Using Pretrained Models: TFIDF weighted W2V on `project_title`
In [196]:
# Similarly you can vectorize for title also
tfidf_model = TfidfVectorizer()
tfidf_model.fit(preprocessed_projectTitle)
# we are converting a dictionary with word as a key, and the idf as a value
dictionary = dict(zip(tfidf_model.get_feature_names(), list(tfidf_model.idf_)))
tfidf_words = set(tfidf_model.get_feature_names())
# average Word2Vec
# compute average word2vec for each review.
tfidf_w2v_vectors_project_title = []; # the avg-w2v for each sentence/review is stored in this list
for sentence in tqdm(preprocessed_projectTitle): # for each review/sentence
vector = np.zeros(300) # as word vectors are of zero length
tf_idf_weight =0; # num of words with a valid vector in the sentence/review
for word in sentence.split(): # for each word in a review/sentence
if (word in glove_words) and (word in tfidf_words):
vec = model[word] # getting the vector for each word
# here we are multiplying idf value(dictionary[word]) and the tf value((sentence.count(word)/len(sentence.split())))
tf_idf = dictionary[word]*(sentence.count(word)/len(sentence.split())) # getting the tfidf value for each word
vector += (vec * tf_idf) # calculating tfidf weighted w2v
tf_idf_weight += tf_idf
if tf_idf_weight != 0:
vector /= tf_idf_weight
tfidf_w2v_vectors_project_title.append(vector)
print(len(tfidf_w2v_vectors_project_title))
print(len(tfidf_w2v_vectors_project_title[0]))
1.4.3 Vectorizing Numerical features¶
In [197]:
# check this one: https://www.youtube.com/watch?v=0HOqOcln3Z4&t=530s
# standardization sklearn: https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html
from sklearn.preprocessing import StandardScaler
# price_standardized = standardScalar.fit(project_data['price'].values)
# this will rise the error
# ValueError: Expected 2D array, got 1D array instead: array=[725.05 213.03 329. ... 399. 287.73 5.5 ].
# Reshape your data either using array.reshape(-1, 1)
price_scalar = StandardScaler()
price_scalar.fit(project_data['price'].values.reshape(-1,1)) # finding the mean and standard deviation of this data
print(f"Mean : {price_scalar.mean_[0]}, Standard deviation : {np.sqrt(price_scalar.var_[0])}")
# Now standardize the data with above maen and variance.
price_standardized = price_scalar.transform(project_data['price'].values.reshape(-1, 1))
In [198]:
price_standardized
Out[198]:
In [199]:
## standardization for teacher_number_of_previously_posted_projects
teacher_number_of_previously_posted_projects_scalar = StandardScaler()
teacher_number_of_previously_posted_projects_scalar.fit(project_data['teacher_number_of_previously_posted_projects'].values.reshape(-1,1)) # finding the mean and standard deviation of this data
print(f"Mean : {teacher_number_of_previously_posted_projects_scalar.mean_[0]}, Standard deviation : {np.sqrt(teacher_number_of_previously_posted_projects_scalar.var_[0])}")
# Now standardize the data with above maen and variance.
teacher_number_of_previously_posted_projects_standardized = teacher_number_of_previously_posted_projects_scalar.transform(project_data['teacher_number_of_previously_posted_projects'].values.reshape(-1, 1))
1.4.4 Merging all the above features¶
- we need to merge all the numerical vectors i.e catogorical, text, numerical vectors
In [200]:
print(categories_one_hot.shape)
print(sub_categories_one_hot.shape)
print(text_bow_vec.shape)
print(price_standardized.shape)
In [201]:
# merge two sparse matrices: https://stackoverflow.com/a/19710648/4084039
from scipy.sparse import hstack
# with the same hstack function we are concatinating a sparse matrix and a dense matirx :)
X = hstack((categories_one_hot, sub_categories_one_hot, text_bow_vec, price_standardized))
X.shape
Out[201]:
Exercise 1: categorical, numerical features + project_title(BOW)¶
In [ ]:
Exercise 2 - categorical, numerical features + project_title(TFIDF)¶
In [202]:
####
In [203]:
Assignment 2: Apply TSNE
If you are using any code snippet from the internet, you have to provide the reference/citations, as we did in the above cells. Otherwise, it will be treated as plagiarism without citations.
- In the above cells we have plotted and analyzed many features. Please observe the plots and write the observations in markdown cells below every plot.
- EDA: Please complete the analysis of the feature: teacher_number_of_previously_posted_projects
-
- Build the data matrix using these features
- school_state : categorical data (one hot encoding)
- clean_categories : categorical data (one hot encoding)
- clean_subcategories : categorical data (one hot encoding)
- teacher_prefix : categorical data (one hot encoding)
- project_grade_category : categorical data (one hot encoding)
- project_title : text data (BOW, TFIDF, AVG W2V, TFIDF W2V)
- price : numerical
- teacher_number_of_previously_posted_projects : numerical
- Now, plot FOUR t-SNE plots with each of these feature sets.
- categorical, numerical features + project_title(BOW)
- categorical, numerical features + project_title(TFIDF)
- categorical, numerical features + project_title(AVG W2V)
- categorical, numerical features + project_title(TFIDF W2V)
- Concatenate all the features and Apply TNSE on the final data matrix
- Note 1: The TSNE accepts only dense matrices
- Note 2: Consider only 5k to 6k data points to avoid memory issues. If you run into memory error issues, reduce the number of data points but clearly state the number of datat-poins you are using
2.1 TSNE with `BOW` encoding of `project_title` feature
In [204]:
labels = project_data['project_is_approved'].replace({0: 'Not Approved', 1: 'Approved'})
labels_limited = labels[:5000]
In [205]:
from sklearn.manifold import TSNE
In [206]:
# please write all of the code with proper documentation and proper titles for each subsection
# when you plot any graph make sure you use
# a. Title, that describes your plot, this will be very helpful to the reader
# b. Legends if needed
# c. X-axis label
exercise_BOW = hstack((categories_one_hot,school_state_one_hot,categories_one_hot,teacher_prefix_one_hot
, sub_categories_one_hot,project_grade_category_one_hot, project_title_bow_vec, price_standardized,teacher_number_of_previously_posted_projects_standardized))
#categorical, numerical features + project_title(BOW)
exercise = exercise_BOW.tocsr()
exercise_new = exercise[0:5000,:]
exercise_new = exercise_new.toarray()
model = TSNE(n_components = 2, perplexity = 100.0, random_state = 0)
tsne_exercise = model.fit_transform(exercise_new)
tsne_exercise = np.vstack((tsne_exercise.T,labels_limited)).T
In [207]:
tsne_exercise_df = pd.DataFrame(tsne_exercise, columns = ("X Axis","Y Axis","Labels"))
s = sns.FacetGrid(tsne_exercise_df, hue = 'Labels', size = 10).map(plt.scatter, "X Axis", "Y Axis").add_legend().fig.suptitle("TSNE with BOW Encoding OF Project Title")
plt.show()
Summary :
- We observe alot of overlapping in the datapoints.
- The points are well scattered, unable to draw any proper conclusion.
2.2 TSNE with `TFIDF` encoding of `project_title` feature
In [208]:
# please write all the code with proper documentation, and proper titles for each subsection
# when you plot any graph make sure you use
# a. Title, that describes your plot, this will be very helpful to the reader
# b. Legends if needed
# c. X-axis label
# d. Y-axis label
exercise_TFIDF = hstack((categories_one_hot,school_state_one_hot,categories_one_hot,teacher_prefix_one_hot
, sub_categories_one_hot,project_grade_category_one_hot, project_title_tfidf_vec, price_standardized,teacher_number_of_previously_posted_projects_standardized))
exercise = exercise_TFIDF.tocsr()
exercise_new = exercise[0:5000,:]
exercise_new = exercise_new.toarray()
model = TSNE(n_components = 2, perplexity = 100.0, random_state = 0)
tsne_exercise = model.fit_transform(exercise_new)
tsne_exercise = np.vstack((tsne_exercise.T,labels_limited)).T
tsne_exercise_df = pd.DataFrame(tsne_exercise, columns = ("X Axis","Y Axis","Labels"))
In [209]:
sns.FacetGrid(tsne_exercise_df, hue = 'Labels', size = 10).map(plt.scatter, "X Axis", "Y Axis").add_legend().fig.suptitle("TSNE with BOW Encoding OF Project Title")
plt.show()
Summary :
The Blue and the Orange points do not form any clusters or accumulation of any type, Hence drawing conclusions seems to quite impossible with the current state of the T-SNE data using TFIDF Encoding
2.3 TSNE with `AVG W2V` encoding of `project_title` feature
In [210]:
# please write all the code with proper documentation, and proper titles for each subsection
# when you plot any graph make sure you use
# a. Title, that describes your plot, this will be very helpful to the reader
# b. Legends if needed
# c. X-axis label
# d. Y-axis label
#categorical, numerical features + project_title(AVG W2V)
exercise_AVG_W2V = hstack((categories_one_hot,school_state_one_hot,categories_one_hot,teacher_prefix_one_hot
, sub_categories_one_hot,project_grade_category_one_hot, avg_w2v_vectors_project_title, price_standardized,teacher_number_of_previously_posted_projects_standardized))
exercise = exercise_AVG_W2V.tocsr()
exercise_new = exercise[0:5000,:]
exercise_new = exercise_new.toarray()
model = TSNE(n_components = 2, perplexity = 100.0, random_state = 0)
tsne_exercise = model.fit_transform(exercise_new)
tsne_exercise = np.vstack((tsne_exercise.T,labels_limited)).T
tsne_exercise_df = pd.DataFrame(tsne_exercise, columns = ("X Axis","Y Axis","Labels"))
In [215]:
sns.FacetGrid(tsne_exercise_df, hue = 'Labels', size = 10).map(plt.scatter, "X Axis", "Y Axis").add_legend().fig.suptitle("TSNE with AVG W2V Encoding OF Project Title")
plt.show()
Summary :
We do not observe any clusters for whether the Project is accepted or not accepted. Hence we are not able to achieve the desired result using Avg- Word2vec
2.4 TSNE with `TFIDF Weighted W2V` encoding of `project_title` feature
In [212]:
# please write all the code with proper documentation, and proper titles for each subsection
# when you plot any graph make sure you use
# a. Title, that describes your plot, this will be very helpful to the reader
# b. Legends if needed
# c. X-axis label
# d. Y-axis label
#categorical, numerical features + project_title(TFIDF W2V)
exercise_TFIDF_W_W2V = hstack((categories_one_hot,school_state_one_hot,categories_one_hot,teacher_prefix_one_hot
, sub_categories_one_hot,project_grade_category_one_hot, tfidf_w2v_vectors_project_title, price_standardized,teacher_number_of_previously_posted_projects_standardized))
exercise = exercise_TFIDF_W_W2V.tocsr()
exercise_new = exercise[0:5000,:]
exercise_new = exercise_new.toarray()
model = TSNE(n_components = 2, perplexity = 100.0, random_state = 0)
tsne_exercise = model.fit_transform(exercise_new)
tsne_exercise = np.vstack((tsne_exercise.T,labels_limited)).T
tsne_exercise_df = pd.DataFrame(tsne_exercise, columns = ("X Axis","Y Axis","Labels"))
In [216]:
sns.FacetGrid(tsne_exercise_df, hue = 'Labels', size = 10).map(plt.scatter, "X Axis", "Y Axis").add_legend().fig.suptitle("TSNE with TFIDF Weighted W2V Encoding OF Project Title")
plt.show()
Summary :
This visualisation of TSNE with TF-IDF Weighted Word2Vec does not seem to yield the expected result of clustering similar data points. Hence we would have to try any other method
Concatenate all the features and Apply TNSE on the final data matrix¶
In [214]:
exercise_all = hstack((categories_one_hot,school_state_one_hot,categories_one_hot,teacher_prefix_one_hot
, sub_categories_one_hot,project_grade_category_one_hot, avg_w2v_vectors_project_title,project_title_tfidf_vec,project_title_bow_vec,tfidf_w2v_vectors_project_title, price_standardized,teacher_number_of_previously_posted_projects_standardized))
exercise = exercise_all.tocsr()
exercise_new = exercise[0:5000,:]
exercise_new = exercise_new.toarray()
model = TSNE(n_components = 2, perplexity = 100.0, random_state = 0)
tsne_exercise = model.fit_transform(exercise_new)
tsne_exercise = np.vstack((tsne_exercise.T,labels_limited)).T
tsne_exercise_df = pd.DataFrame(tsne_exercise, columns = ("X Axis","Y Axis","Labels"))
sns.FacetGrid(tsne_exercise_df, hue = 'Labels', size = 10).map(plt.scatter, "X Axis", "Y Axis").add_legend().fig.suptitle("TSNE with All the feature")
plt.show()
2.5 Summary
In [ ]:
# Write few sentences about the results that you obtained and the observations you made.
Summary :¶
This visualisation of TSNE with Bag of Words, TF-IDF, Avg Word2Vec, TF-IDF Weighted Word2Vec does not seem to yield the expected result of clustering similar data points. Hence we would have to try any other method.
2.6 CONCLUSION¶
- Delaware (DE) state from the United States has the highest percent of projects accepted within the whole country having almost 90% acceptance rate, followed by North Dakota (ND) and Washington (WA) nearly 89% and 88% respectively each.
- Vermont (VT) has the lowest Approval rate with exactly 80% followed by District of Columbia (DC) and Texas (TX) with nearly 80% and 81% respectively.
- Female Teachers have the maximum number of projects proposed and accepted compared to the male teachers.
- There are alot of projects proposed for the students between Pre Kindergarden and 2nd Grade while for the rest it keeps decreasing as the Grades increase.
- We also notice that Students between the 9th Grade and 12th Grade have the lowest number of projects proposed as well as accepted.
- Projects belonging to the Literacy and Language categories have the highest number of projects proposed under. The maximum number of accepted projects also belong to this category, having an acceptance rate of nearly 87%.
- Projects belonging to both Maths and Science have acceptance rate of nearly 82% while introducing the concept of Literacy and Language to this can increase its accpetance rate to nearly 87%
- Projects belonging to both Maths and Science when combined with Applied Learning has the least number of projects.
- There is also Variability in Acceptance rate, projects under the category Warmth, Care and Hunger have an accpetance rate of 93.5%
- The highest number of projects are registered under Literacy and Langauage with 52,239
- The highest number of projects are registered under Literacy and Langauage with 52,239 projects, followed by Maths and Science having 41,421 projects.
- The sub-Category Literacy has the highest number of projects approved with 8371 projects. Also the accpetance rate is 88%.
- The sub-Category Health and Wellness have the lowest number of projects proposed with 3,583 projects only.
- Roughly most of the projects have 3, 4 or 5 words in the title.There are hardly any project titles containing more than 10 words.
- The number of words in the Project Essays of Approved Projects are slightly more than the number of words in the Project Essays of the Rejected Projects.
- The Maximum price for any project should be less than 10,000 dollars.The approved projects tend to have lower cost when compared to the projects that have not been approved.
- We observe that it is not mandatory for a teacher to have proposed any project prior. Maximum number of teachers, nearly 82% of the approved projects have been submitted by teachers with no prior project proposals. New talent and efforts are well appreciated.
- Very few teachers who have proposed more than 20 projects have got approval. But the rate of approval is Higher given the teacher has proposed atleast 19 different projects.
- The project summaries containing numeric values have a very high acceptance rate of 90%. Well, proper numbered requirements suggest clarity in the proposals and hence Alot of people tend to donate for a better cause, that is to help children.
- We observe that on an average Each project costs nearly 298 Dollars. The Price paid is generally for the purchase of the Items. The projects on an average require atleast 17 Different of similar items.
- Visualisation of TSNE with Bag of Words, TF-IDF, Avg Word2Vec, TF-IDF Weighted Word2Vec does not seem to yield the expected result of clustering similar data points. Hence we would have to try any other method.